“Code generation”

Open-source infrastructure that runs AI-generated code in isolated cloud sandboxes.

Code sandboxes built from Docker-image snapshots for running agent and model-generated code, with Python and TypeScript SDKs.

Isolated Linux microVMs for running agent-generated or untrusted code, driven by an SDK and CLI.

Open-source multi-agent coding system from the HKU Data Intelligence Lab, written in Python

CPU and GPU machines and sandboxes for agents, billed by the millisecond, with VMs that pause with memory intact.

Apache-2.0 drag-and-drop studio for AG2 multi-agent apps that generates self-contained Python code.

Multi-agent development platform built on Kotlin Multiplatform, with IDE plugins, a CLI, desktop, mobile and web targets.

Python command-line pairing agent for ML engineers that builds baselines, works Kaggle-style tasks and writes weekly reports.

Open-source end-to-end general multi-agent product that answers queries and produces reports, slides and code.

Open-source terminal agent that queries and edits codebases and automates tasks with Gemini models

Open-source self-evolving general AI agent with a Docker sandbox that can run fully local on Ollama or vLLM models.

Open-source platform where you configure multi-agent systems and workflows without writing code

AI gateway giving one API to 250+ models, with observability, guardrails and prompt management.

Open-source super agent harness that runs sub-agents, memory, sandboxes and skills for research, coding and content tasks lasting minutes to hours.

Free open-source desktop app for Windows and macOS that runs AI agents with one-click install, sandboxed workspaces and Skills.

Windows desktop AI companion built on Electron with a Live2D character, long-term memory, voice and tool calling.

Open-source generative BI engine that gives AI agents a governed semantic layer for correct SQL and shareable dashboards.

Retrieval augmented generation package that answers questions from scientific papers and documents with citations.

Game-style visual builder for AI agents, with WeChat channel binding, a ReAct code assistant and an orchestrator service.

AI app builder from Convex that generates full-stack web apps with a built-in database, auth and background workflows.

Multi-agent platform that audits source code for vulnerabilities, verifies findings and drafts CVE reports

Personal research assistant for scientific work, built on LangChain DeepAgents with an isolated Docker sandbox.

Desktop AI agent that runs on your machine, edits project files and runs commands, and produces Word, Excel, PowerPoint and PDF files.